Projects

Selected work

Research directions, experiments, and engineering projects in computer vision and multimodal AI.

Computer Vision · Geospatial AI

Learning visual representations to estimate where a photograph was captured.

Computer Vision · Visual Retrieval

Recognizing places across viewpoint changes and challenging indoor environments.

Multimodal AI · Retrieval

Combining visual embeddings and contextual reasoning to improve location candidates.

Trust & Safety · Computer Vision

A planned detection platform for AI-generated imagery and face manipulation.

Fine-Grained Visual Recognition

Fine-grained vehicle recognition from large-scale image collections.